Fine-grained image classification method based on sparse bilinear convolutional neural network

Abstract

The invention relates to a fine-grained image classification method based on a sparse bilinear convolutional neural network, and the method comprises the steps: carrying out the feature channel cutting of the bilinear convolutional neural network, automatically thinning feature channels in a training process, distinguishing the importance of the feature channels for classification, and carrying out the scale cutting according to the importance; inputting the output of the bilinear convolutional neural network into the batch regularization; taking a scaling factor of BN as a scale factor; applying a regularization method to the scale factor, wherein the regularization method has a plurality of types such as L1 and L2, the sparsity of L1 is strong, the sparsity of the feature channels can be realized by jointly training the network weight and the scale factor; finally, performing pruning according to the size sequence of the sparse scale factor, and finally, obtaining a model for finally performing a fine-grained image classification task by utilizing fine tuning. Weak supervision can be realized, redundant parameters are reduced, overfitting is prevented, and the accuracy of fine-grained image classification is effectively improved.

Description

technical field [0001] The invention relates to an image processing technology, in particular to a fine-grained image classification method based on a sparse bilinear convolutional neural network. Background technique [0002] Fine-grained image classification based on ordinary convolutional neural networks can only use strong supervised learning methods in order to obtain better classification results. Training pictures requires a lot of manual labeling information, while some better weakly supervised learning methods only require pictures to have labels. However, due to too many parameters, it is easy to cause overfitting, and the accuracy of training is quite different from the accuracy of testing. Contents of the invention [0003] The present invention aims at the existing problems of fine-grained image classification based on ordinary convolutional neural network, and proposes a fine-grained image classification method based on sparse bilinear convolutional neural ne...

AI Technical Summary

Problems solved by technology

[0002] Fine-grained image classification based on ordinary convolutional neural networks can only use strong supervised learning methods in order to obtain better classification results. Training pictures requires a lot of manual labeling information, while some better weakly supervised learning methods only require pictures to have labels. However, due to too many parameters, it is easy to cause overfitting, and the accuracy of training is quite different from the accuracy of testing.

Images